Leaderboard Explore Compare Profile Community Blog FAQ Competition 2024 Report Issue

Sample stimuli

How to use

from brainscore_vision import load_benchmark
benchmark = load_benchmark("Papale2025.IT-ridgecv")
score = benchmark(my_model)

Benchmark API

Code examples

Model scores

Score Legend Min Alignment Max Alignment

Rank	Model	Score
1	resnext101_32x48d_wsl	.632
2	vit_large_patch14_clip_224:laion2b_ft_in12k_in1k	.618
3	resnet50-moclr8deg	.612
4	resnext101_32x16d_wsl	.612
5	dinov2_vitl14_lc	.612
6	regnety_032	.604
7	resnext101_32x32d_wsl	.596
8	vit_large_patch14_clip_224:openai_ft_in12k_in1k	.594
9	convnext_xxlarge_clip	.592
10	resnet50-SIN_IN_IN	.592
11	seresnext50_32x4d	.591
12	antialiased-r50	.590
13	focalnet_tiny_lrf_in1k	.590
14	resnet_50_v1_spiking	.587
15	resnet_50_v1	.587
16	resnet50-sup	.587
17	vit_huge_patch14_clip_224:laion2b_ft_in12k_in1k	.586
18	vit_large_patch14_clip_224:openai_ft_in1k	.584
19	vit_base_patch16_clip_224:openai_ft_in12k_in1k	.583
20	resnet50-vitoimagevidnet8	.581
21	resnet50-VITO-8deg-cc	.581
22	Res2Net50_26w_4s	.581
23	resnet50-SIN_IN	.579
24	resnet50_ewconplus_wzc	.576
25	densenet-121	.575
26	convnext_base:clip_laiona_augreg_ft_in1k_384	.574
27	voneresnet-50-non_stochastic	.572
28	dinov2_vitl14_reg_lc_featread	.571
29	dinov2_vitl14_reg_lc	.571
30	convnext_tiny_sup	.571
31	resnet50_robust_l2_eps1	.567
32	AdvProp_efficientnet-b7	.565
33	vit_base_patch16_clip_224:openai_ft_in1k	.565
34	deit_large_imagenet_full_seed-0	.564
35	voneresnet-50	.564
36	resnet50_tutorial	.563
37	vit_relpos_base_patch16_clsgap_224:sw_in1k	.562
38	ReAlnet03_cornet	.562
39	AdvProp_efficientnet-b6	.560
40	convnext_xxlarge:clip_laion2b_soup_ft_in1k	.560
41	VOneCORnet-S	.559
42	vit_tiny_r_s16_p8_384:augreg_in21k_ft_in1k	.559
43	ReAlnet01_cornet	.557
44	ReAlnet04_cornet	.557
45	efficientnet_b0	.556
46	convnext_tiny:in12k_ft_in1k	.554
47	AdvProp_efficientnet-b4	.550
48	pnasnet_large_halfPrecision	.548
49	resnet_SIN_IN_FT_IN	.547
50	resnet152_imagenet_full	.546
51	AT_efficientnet-b2	.545
52	AdvProp_efficientnet-b2	.545
53	vit_large_patch14_clip_224:laion2b_ft_in1k	.545
54	convnext_large_imagenet_full_seed-0	.543
55	shufflenet_v2_x1_0	.542
56	efficientnet_b2_imagenet_full	.540
57	resnet50_st_wzc_seed3_2_323	.538
58	convnext_large:fb_in22k_ft_in1k	.536
59	AdvProp_efficientnet-b8	.536
60	swin_small_patch4_window7_224:ms_in22k_ft_in1k	.535
61	deit_base_imagenet_full_seed-0	.534
62	convnext_base_imagenet_full_seed-0	.534
63	resnet50_st_wzc_seed6_2_323	.532
64	convnext_large_mlp:clip_laion2b_augreg_ft_in1k_384	.531
65	resnet50_st_wzc_seed7_2_323	.530
66	ViT_L_32_imagenet1k	.528
67	vit_relpos_base_patch32_plus_rpn_256:sw_in1k	.527
68	resnet50_ewconplus_wzc_seed5_2__323	.526
69	deit_small_imagenet_full_seed-0	.525
70	resnet50_imagenet_full	.524
71	resnet50_ewconplus_wzc_seed6_2_323	.524
72	effnetb1_272x240	.523
73	resnet50_ewconplus_wzc_seed2_2__323	.523
74	mobilenet_v2_1_4_224	.521
75	convnext_femto_ols:d1_in1k	.520
76	resnext101_32x8d_wsl	.507
77	predictive_coding_pc	.506
78	resnet50-SIN	.505
79	resnet_50_v2	.504
80	custom_model_cv_18_dagger_408	.504
81	resnet-50-robust	.502
82	cvt_cvt-13-384-in1k_4_LucyV4	.498
83	eicircuit_resnet18_bn_20260919	.497
84	cvt_cvt-21-384-in1k_4_LucyV4	.495
85	AlexNet_SIN_fov12	.490
86	convnext_small_imagenet_full_seed-0	.483
87	cvt_cvt-21-384-in22k_finetuned-in1k_4_LucyV4	.479
88	cvt_cvt-13-224-in1k_4_LucyV4	.476
89	AlexNet_SIN_fov16	.475
90	effnetb1_cutmix_augmix_sam_e1_5avg_424x377	.467
91	convnext_tiny_imagenet_full_seed-0	.463
92	convnext_xlarge:fb_in22k_ft_in1k	.459
93	cvt_cvt-13-384-in22k_finetuned-in1k_4_LucyV4	.453
94	grcnn	.448
95	convnext_base_fb_in1k	.442
96	cvt_cvt-21-224-in1k_4_LucyV4	.440
97	effnetb1_cutmixpatch_SAM_robust32_avge6e8e9e10_manylayers_324x288	.423
98	effnetb1_cutmixpatch_augmix_robust32_avge4e7_manylayers_324x288	.412
99	pr1_stl10_disentangled_alpha04	.401
100	AlexNet_SIN	.353
101	ReAlnet01_cornet_fov4	.316
102	resnet18_fair	.279
103	hmax	.171
104	alexnet_training_seed_02	.164
105	alexnet_training_seed_09	.159
106	alexnet_training_seed_03	.155
107	alexnet_training_seed_01	.151
108	alexnet_training_seed_10	.140
109	alexnet_training_seed_06	.135
110	alexnet_training_seed_07	.124
111	gabor_filter_mean_abs_4x4_v2	.101
112	gabor_filter_entropy_4x4	.083
113	gabor_filter_entropy_4x4_v2_forcedCosine	.078
114	gabor_filter_entropy_4x4_v2	.077
115	compact_resnet50_robust_V4	.066
116	vit_huge_clip336_laion
117	vit_large_clip336_openai
118	dinov2_vitl14_lc_res336
119	eva02_large_in22k
120	dinov2_vitg14_reg_lc
121	dinov2_vitg14_lc
122	cvt_cvt-w24-384-in22k_finetuned-in1k_4
123	vit_large_patch14_clip_336:openai_ft_in12k_in1k
124	vit_large_patch14_clip_336:laion2b_ft_in1k

Benchmark bibtex

@article{papale_extensive_2025,
	title = {An extensive dataset of spiking activity to reveal the syntax of the ventral stream},
	volume = {113},
	issn = {08966273},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S089662732400881X},
	doi = {10.1016/j.neuron.2024.12.003},
	journal = {Neuron},
	author = {Papale, Paolo and Wang, Feng and Self, Matthew W. and Roelfsema, Pieter R.},
	year = {2025},
}

Ceiling

0.98.

Note that scores are relative to this ceiling.

Data: Papale2025.IT

Metric: ridgecv